Triple
T23842547
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thurn und Taxis Palace |
E591025
|
entity |
| Predicate | convertedToPalaceFor |
P16372
|
FINISHED |
| Object | Thurn und Taxis family |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Thurn und Taxis family | Statement: [Thurn und Taxis Palace, convertedToPalaceFor, Thurn und Taxis family]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: convertedToPalaceFor Context triple: [Thurn und Taxis Palace, convertedToPalaceFor, Thurn und Taxis family]
-
A.
associatedWithPalace
Indicates a relationship where an entity has a connection, link, or involvement with a palace, such as through location, function, ownership, or affiliation.
-
B.
palace
Indicates that an entity is a palace, i.e., a grand official residence typically used by royalty or high-ranking authorities.
-
C.
rebuiltAsPalace
chosen
Indicates that a structure or building was reconstructed or transformed into a palace.
-
D.
convertedToMausoleum
Indicates that something has been transformed from its original state or use into a mausoleum, typically for the purpose of serving as a burial or memorial structure.
-
E.
hasSwitchPalace
Indicates that a level or area contains or is associated with a Switch Palace.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69e25d1de32c8190a907afe9c3d6cd6d |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f1c888c13c8190b85d2cd425ee84dc |
completed | April 29, 2026, 8:59 a.m. |
| PD | Predicate disambiguation | batch_69f1614612b481908c45d99e588882f9 |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:09 p.m.